Qwen3.8 125B (6B active) Flash-Next

on NVIDIA RTX 5090 · Strata · 4,096 ctx

Oct 11, 2026

Throughput

193.8 t/s gen · 4627.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

IQ3_XXS (GGUF)

KV cache

INT8

System RAM

128 GB

VRAM reported

32 GB

Summary

User benchmarks Qwen3.8-Flash-Next IQ3_XXS at 193.8 t/s generation and 4627.2 t/s prompt processing on an RTX 5090 with 128GB system RAM. Setup is Strata 0.1.40 with INT8 KV cache, 4096-token context, MTP speculation with --spec 4, and CPU expert-pool offload. The IQ3_XXS GGUF is 75.84 GB with 22.34 GiB of GPU expert cache. User compares three quants: IQ3_XXS (193.8 t/s at 4K), IQ3_S (161.0 t/s), and UD-IQ4_XS (116.3 t/s). Accuracy screening on 14 MMLU-Pro questions scored 12/14 for all three. IQ3_XXS had the highest median generation speed in the 4K test.

View source ↗